Enforcing Morphological Information in Fully Convolutional Networks to Improve Cell Instance Segmentation in Fluorescence Microscopy Images
This work addresses accurate cell segmentation for cancer dynamics analysis, enabling more precise treatments, but it is incremental as it builds on existing U-Net methods.
The authors tackled the problem of cell instance segmentation in fluorescence microscopy images, which is challenging due to high cell concentration and overlapping edges, by proposing a novel approach based on U-Net with a deep distance transformer to enforce morphological learning, resulting in a performance boost over traditional U-Net architectures.
Cell instance segmentation in fluorescence microscopy images is becoming essential for cancer dynamics and prognosis. Data extracted from cancer dynamics allows to understand and accurately model different metabolic processes such as proliferation. This enables customized and more precise cancer treatments. However, accurate cell instance segmentation, necessary for further cell tracking and behavior analysis, is still challenging in scenarios with high cell concentration and overlapping edges. Within this framework, we propose a novel cell instance segmentation approach based on the well-known U-Net architecture. To enforce the learning of morphological information per pixel, a deep distance transformer (DDT) acts as a back-bone model. The DDT output is subsequently used to train a top-model. The following top-models are considered: a three-class (\emph{e.g.,} foreground, background and cell border) U-net, and a watershed transform. The obtained results suggest a performance boost over traditional U-Net architectures. This opens an interesting research line around the idea of injecting morphological information into a fully convolutional model.